Update README.md

README.md

@@ -10,9 +10,9 @@ This repository contains CPU-optimized GGUF quantizations of the Meta-Llama-3.1-
 ## Available Quantizations
 
 1. Q4_0_4_8 (CPU FMA-Optimized): ~246 GB
-2. BF16: ~820 GB
-3. Q8_0: ~410 GB
-4. more coming...
+2. BF16: ~811 GB
+3. Q8_0: ~406 GB
+4. Q2-Q8mix ~ 165Gb
 
 ## Use Aria2 for parallelized downloads, links will download 9x faster
 
@@ -33,6 +33,15 @@ aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00005-of-00006.gg
 aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-optimized-q4048-00006-of-00006.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-optimized-q4048-00006-of-00006.gguf
 ```
 
+### Q2K-Q8 Mixed 2bit 8bit I wrote myself. This is the smallest coherent one I could make without yet doing imatrix
+
+```verilog
+aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-2kmix8k-00001-of-00004.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-2kmix8k-00001-of-00004.gguf?download=true
+aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-2kmix8k-00002-of-00004.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-2kmix8k-00002-of-00004.gguf?download=true
+aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-2kmix8k-00003-of-00004.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-2kmix8k-00003-of-00004.gguf?download=true
+aria2c -x 16 -s 16 -k 1M -o meta-405b-inst-cpu-2kmix8k-00004-of-00004.gguf https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/resolve/main/meta-405b-inst-cpu-2kmix8k-00004-of-00004.gguf?download=true
+```
+
 ### BF16 Version
 
 ```bash